检索结果-内蒙古大学图书馆

interactive image segmentation combining global seeding and sparse local reconstruction

PATTERN ANALYSIS AND APPLICATIONS 2025年第2期28卷 1-23页

作者： Long, Jianwu Liu, Yuanqin Zhang, Kaixin Chen, Shuang Luo, Qi Chongqing Univ Technol Coll Comp Sci & Engn Chongqing 400054 Peoples R China

Seed segmentation methods are highly regarded for their effectiveness in processing complex images, user-friendliness, and compatibility with graph-based representations. However, these methods often depend on intricate computational tools, leading to issues such as poor image contour adherence and incomplete seed propagation. To address these limitations, this paper proposes an interactive framework that integrates global seed information with sparse local linear reconstruction regularization (GSSR). In this framework, a Gaussian mixture model is firstly employed to construct a flow of global seed information, establishing connections between pixel points and yielding more complete segmented objects. Additionally, the L-p(0 < p <= 1) norm is utilized to constrain the sparse local reconstruction term, facilitating the generation of sparse boundaries. An iterative process based on the Alternating Direction Method of Multipliers (ADMM) is developed to solve the L1 regularization term, which is then generalized for the L-p problem through reweighting. We conduct a comprehensive comparison on the BSD dataset, CVC-ClinicDB datasets and two publicly available MSRC datasets with different labeling schemes. Extensive experimental validation demonstrates that the proposed method outperforms existing *** source code and datasets are openly available at: https://***/choppy-water/GSSR.

关键词： interactive image segmentation Sparse regularity Local linear reconstruction Global seed diffusion model

来源：评论

学校读者我要写书评

暂无评论

PVPUFormer: Probabilistic Visual Prompt Unified Transformer for interactive image segmentation

引用

IEEE TRANSACTIONS ON image PROCESSING 2024年 33卷 6455-6468页

作者： Zhang, Xu Yang, Kailun Lin, Jiacheng Yuan, Jin Li, Zhiyong Li, Shutao Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Hunan Univ Natl Engn Res Ctr Robot Visual Percept & Control T Sch Robot Changsha 410082 Peoples R China

Integration of diverse visual prompts like clicks, scribbles, and boxes in interactive image segmentation significantly facilitates users' interaction as well as improves interaction efficiency. However, existing studies primarily encode the position or pixel regions of prompts without considering the contextual areas around them, resulting in insufficient prompt feedback, which is not conducive to performance acceleration. To tackle this problem, this paper proposes a simple yet effective Probabilistic Visual Prompt Unified Transformer (PVPUFormer) for interactive image segmentation, which allows users to flexibly input diverse visual prompts with the probabilistic prompt encoding and feature post-processing to excavate sufficient and robust prompt features for performance boosting. Specifically, we first propose a Probabilistic Prompt-unified Encoder (PPuE) to generate a unified one-dimensional vector by exploring both prompt and non-prompt contextual information, offering richer feedback cues to accelerate performance improvement. On this basis, we further present a Prompt-to-Pixel Contrastive (P2C) loss to accurately align both prompt and pixel features, bridging the representation gap between them to offer consistent feature representations for mask prediction. Moreover, our approach designs a Dual-cross Merging Attention (DMA) module to implement bidirectional feature interaction between image and prompt features, generating notable features for performance improvement. A comprehensive variety of experiments on several challenging datasets demonstrates that the proposed components achieve consistent improvements, yielding state-of-the-art interactive segmentation performance. Our code is available at https://***/XuZhang1211/PVPUFormer.

关键词： image segmentation Visualization Probabilistic logic image coding Vectors Transformers Feature extraction Encoding Merging Robots interactive image segmentation transformer visual prompt contrastive loss

来源：评论

学校读者我要写书评

暂无评论

CGAN: lightweight and feature aggregation network for high-performance interactive image segmentation

引用

VISUAL COMPUTER 2024年第3期40卷 2203-2217页

作者： Yan, Gui Zhengyan, Zhang Zhihua, Chen Chuang, Zhang Jin, Zhang Changsha Univ Sci & Technol Sch Comp & Commun Engn Changsha 410114 Hunan Peoples R China Changsha Univ Sci & Technol Hunan Prov Key Lab Intelligent Proc Big Data Trans Changsha 410114 Hunan Peoples R China East China Univ Sci & Technol Dept Comp Sci & Engn Shanghai 200237 Peoples R China

In the task of interactive image segmentation, user interactions about the object of interest are accepted to predict the segmentation mask. Recent works have demonstrated state-of-the-art results by using either backpropagating refinement or iterative training scheme, which are computationally expensive. In this paper, we propose a novel method for interactive image segmentation using conditional generative adversarial networks to enforce higher-order consistency in the segmentation, without extra post-processing during inference. Concretely, we develop a new segmentation network which integrates three different modules by providing global contextual information and attentions and conducting feature fusions across multiple layers. This allows the segmentation network to learn strong object representations and predict more accurate segmentations. We then employ a fully convolutional discriminator to detect and correct higher-order inconsistency between the predictions of the segmentation network and the ground truth label maps. To achieve this, we optimize an objective function that combines the conventional segmentation loss with the adversarial loss of the adversarial term. We train our network on the Pascal VOC 2012 and MS COCO 2017 datasets and conduct comprehensive experiments on four benchmark datasets. Experimental results show that the adversarial training to the network architecture has improved segmentation results over state-of-the-art methods, while making the current system efficient in terms of speed.

关键词： interactive image segmentation Conditional generative adversarial network Adversarial learning Feature aggregation network Higher-order consistency

来源：评论

学校读者我要写书评

暂无评论

Implementation and analysis of quantum-classical hybrid interactive image segmentation algorithm based on quantum annealer

引用

QUANTUM INFORMATION PROCESSING 2024年第8期23卷 1-22页

作者： Wang, Kehan Wang, Shuang Chen, Qinghui Qiao, Xingyu Ma, Hongyang Qiu, Tianhui Qingdao Univ Technol Sch Sci Qingdao 266033 Peoples R China Qingdao Univ Technol Sch Informat & Control Engn Qingdao 266033 Peoples R China

With the development of computer vision and digital image processing technology, image segmentation has become an important part of various image processing and image analysis. Since interactive segmentation can obtain more accurate results than automatic segmentation, the most representative Graph Cuts has gradually become a popular method in image segmentation. However, this algorithm has two significant disadvantages. On the one hand, if the background is complex or very similar to the foreground, the accuracy will be low;on the other hand, the algorithm is slow and the iteration process is complicated. To improve it, this paper proposes a new image segmentation algorithm based on quantum annealing and Graph Cuts. The algorithm beds the classical interactive image segmentation problem into a quantum optimization algorithm and obtains ideal image segmentation results on the D-Wave quantum annealer. Meanwhile, it is compared with the other three methods. Compared with MATLAB, the segmentation results are more beautiful, with an average precision higher than 5.27% and an average recall higher than 5.43%;the quantum annealing time is always lower than the simulated annealing time;and the success probability is more than twice that of the quantum approximate optimization algorithm. Therefore, it is concluded that this method is superior.

关键词： Quantum annealing interactive image segmentation D-Wave quantum annealer QUBO Graph Cuts

来源：评论

学校读者我要写书评

暂无评论

Grouping Boundary Proposals for Fast interactive image segmentation

引用

IEEE TRANSACTIONS ON image PROCESSING 2024年 33卷 793-808页

作者： Liu, Li Chen, Da Shu, Minglei Cohen, Laurent D. Qilu Univ Technol Shandong Artificial Intelligence Inst Shandong Acad Sci Jinan 250014 Peoples R China Univ Paris 09 PSL Res Univ CNRS CEREMADEUMR 7534 F-75016 Paris France

Geodesic models are known as an efficient tool for solving various image segmentation problems. Most of existing approaches only exploit local pointwise image features to track geodesic paths for delineating the objective boundaries. However, such a segmentation strategy cannot take into account the connectivity of the image edge features, increasing the risk of shortcut problem, especially in the case of complicated scenario. In this work, we introduce a new image segmentation model based on the minimal geodesic framework in conjunction with an adaptive cut-based circular optimal path computation scheme and a graph-based boundary proposals grouping scheme. Specifically, the adaptive cut can disconnect the image domain such that the target contours are imposed to pass through this cut only once. The boundary proposals are comprised of precomputed image edge segments, providing the connectivity information for our segmentation model. These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them. Experimental results show that the proposed model indeed outperforms state-of-the-art minimal paths-based image segmentation approaches.

关键词： interactive image segmentation circular paths boundary proposal grouping fast marching method Eikonal equation

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised interactive image segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第8期34卷 6797-6808页

作者： Shi, Qingxuan Li, Yihang Di, Huijun Wu, Enyi Hebei Univ Hebei Machine Vis Engn Res Ctr Baoding 071000 Peoples R China Hebei Univ Sch Cyber Secur & Comp Baoding 071000 Peoples R China Beijing Inst Technol Sch Comp Sci Beijing 100811 Peoples R China

Although interactive image segmentation techniques have made significant progress, supervised learning-based methods rely heavily on large-scale labeled data which is difficult to obtain in certain domains such as medicine, biology, etc. Models trained on natural images also struggle to achieve satisfactory results when directly applied to these domains. To solve this dilemma, we propose a Self-supervised interactive segmentation (SIS) method that achieves superior generalization performance. By clustering features from unlabeled data, we obtain classifiers that assign pseudo-labels to pixels in images. After refinement by super-pixel voting, these pseudo-labels are then used to train our segmentation network. To enable our network to better adapt to cross-domain images, we introduce correction learning and anti-forgetting regularization to conduct test-time adaptation. Our experiment results on five datasets show that our approach significantly outperforms other interactive segmentation methods across natural image datasets in the same conditions and achieves even better performance than some supervised methods when across to medical image domain. The code and models are available at https://***/leal0110/SIS.

关键词： image segmentation Feature extraction Task analysis Medical diagnostic imaging Training Adaptation models Annotations interactive image segmentation self-supervised learning test-time adaptation generalization

来源：评论

学校读者我要写书评

暂无评论

Click-Pixel Cognition Fusion Network With Balanced Cut for interactive image segmentation

引用

IEEE TRANSACTIONS ON image PROCESSING 2024年 33卷 177-190页

作者： Lin, Jiacheng Xiao, Zhiqiang Wei, Xiaohui Duan, Puhong He, Xuan Dian, Renwei Li, Zhiyong Li, Shutao Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Peoples R China Hunan Normal Univ Coll Informat Sci & Engn Changsha 410081 Peoples R China Coll Elect & Informat Engn Changsha 410082 Hunan Peoples R China Hunan Univ Key Lab Visual Percept & Artificial Intelligence H Changsha 410082 Peoples R China Hunan Univ Sch Robot Changsha 410012 Peoples R China

interactive image segmentation (IIS) has been widely used in various fields, such as medicine, industry, etc. However, some core issues, such as pixel imbalance, remain unresolved so far. Different from existing methods based on pre-processing or post-processing, we analyze the cause of pixel imbalance in depth from the two perspectives of pixel number and pixel difficulty. Based on this, a novel and unified Click-pixel Cognition Fusion network with Balanced Cut (CCF-BC) is proposed in this paper. On the one hand, the Click-pixel Cognition Fusion (CCF) module, inspired by the human cognition mechanism, is designed to increase the number of click-related pixels (namely, positive pixels) being correctly segmented, where the click and visual information are fully fused by using a progressive three-tier interaction strategy. On the other hand, a general loss, Balanced Normalized Focal Loss (BNFL), is proposed. Its core is to use a group of control coefficients related to sample gradients and forces the network to pay more attention to positive and hard-to-segment pixels during training. As a result, BNFL always tends to obtain a balanced cut of positive and negative samples in the decision space. Theoretical analysis shows that the commonly used Focal and BCE losses can be regarded as special cases of BNFL. Experiment results of five well-recognized datasets have shown the superiority of the proposed CCF-BC method compared to other state-of-the-art methods. The source code is publicly available at https://***/lab206/CCF-BC.

关键词： Task analysis Visualization image segmentation Cognition Training Transforms Optimization Click-pixel fusion pixel imbalance problem balanced normalized focal loss interactive image segmentation

来源：评论

学校读者我要写书评

暂无评论

Spiking Neural P System with weight model of majority voting technique for reliable interactive image segmentation

引用

NEURAL COMPUTING & APPLICATIONS 2023年第12期35卷 9035-9051页

作者： Dalvand, Mehran Fathi, Abdolhossein Kamran, Arezoo Razi Univ Dept Comp Engn & Informat Technol Kermanshah Iran

interactive image segmentation is a method for precisely segmenting of the object from background using information entered by the user. However, most interactive segmentation techniques are sensitive to the location and the number of seed points. To obtain a satisfactory result, the user should repeat the segmentation process over and over, and also based on employed technique, it may work well in some limited conditions and applications. To overcome these limitations and enhance the robustness of interactive image segmentation algorithm, this paper proposes a parallel fusion model using the majority voting technique, which not only is more reliable than existing methods, but also requires less user interaction. To this end, at first the input image is segmented by several segmentation methods independently. Then the obtained results are combined using majority voting technique to extract final segmentation result. To reduce the computational overhead of the proposed scheme, a spiking neural-like P system model for parallel implementation of majority voting technique is also proposed. The proposed model has been evaluated and compared with state-of-the-art methods using different metrics, and the obtained results show its efficiency compared to other methods.

关键词： interactive image segmentation Majority voting Spiking neural-like P system Membrane computing

来源：评论

学校读者我要写书评

暂无评论

interactive image segmentation of MARS Datasets Using Bag of Features

引用

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2021年第4期5卷 559-567页

作者： Kanithi, Praveenkumar de Ruiter, Niels J. A. Amma, Maya R. Lindeman, Robert W. Butler, Anthony P. H. Butler, Philip H. Chernoglazov, Alexander I. Mandalika, V. B. H. Adebileje, Sikiru A. Alexander, Steven D. Anjomrouz, Marzieh Asghariomabad, Fatemeh Atharifard, Ali Atlas, James Bamford, Benjamin Bell, Stephen T. Bheesette, Srinidhi Carbonez, Pierre Chambers, Claire Clark, Jennifer A. Colgan, Frances Crighton, Jonathan S. Dahal, Shishir Damet, Jerome Doesburg, Robert M. N. Duncan, Neryda Ghodsian, Nooshin Gieseg, Steven P. Goulter, Brian P. Gurney, Sam Healy, Joseph L. Kirkbride, Tracy Lansley, Stuart P. Lowe, Chiara Marfo, Emmanuel Matanaghi, Aysouda Moghiseh, Mahdieh Palmer, David Panta, Raj K. Prebble, Hannah M. Raja, Aamir Y. Renaud, Peter Sayous, Yann Schleich, Nanette Searle, Emily Sheeja, Jereena S. Uddin, Rayhan Vanden Broeke, Lieza Vivek, V. S. Walker, E. Peter Walsh, Michael F. Wijesooriya, Manoj Younger, W. Ross Univ Canterbury Human Interface Technol Lab New Zealand Christchurch 8140 New Zealand MARS Bioimaging Ltd Christchurch 8140 New Zealand Univ Canterbury Sch Phys & Chem Sci Christchurch 8140 New Zealand Univ Otago Christchurch Dept Radiol Christchurch 8011 New Zealand Univ Canterbury Christchurch 8140 New Zealand European Org Nucl Res CERN CH-1211 Geneva Switzerland Ara Inst Canterbury Christchurch 8011 New Zealand Minist Hlth Kathmandu 44600 Nepal Natl Acad Med Sci Kathmandu 44600 Nepal Univ Lausanne Hosp Inst Radiat Phys CH-1011 Lausanne Switzerland Lincoln Univ Dept Wine Food & Mol Biosci Lincoln 7647 New Zealand Univ Otago Dept Radiat Therapy Wellington 6242 New Zealand

In this article, we propose a slice-based interactive segmentation of spectral CT datasets using a bag of features method. The data are acquired from a MARS scanner that divides up the X-ray spectrum into multiple energy bins for imaging. In literature, most existing segmentation methods are limited to performing a specific task or tied to a particular imaging modality. Therefore, when applying generalized methods to MARS datasets, the additional energy information acquired from the scanner cannot be sufficiently utilized. We describe a new approach that circumvents this problem by effectively aggregating the data from multiple channels. Our method solves a classification problem to get the solution for segmentation. Starting with a set of labeled pixels, we partition the data using superpixels. Then, a set of local descriptors, extracted from each superpixel, are encoded into a codebook and pooled together to create a global superpixel-level descriptor (bag of features representation). We propose to use the vector of locally aggregated descriptors as our encoding/pooling strategy, as it is efficient to compute and leads to good results with simple linear classifiers. A linear support vector machine is then used to classify the superpixels into different labels. The proposed method was evaluated on multiple MARS datasets. Experimental results show that our method achieved an average of more than 10% increase in the accuracy over other state-of-the-art methods.

关键词： Bag of features interactive image segmentation MARS imaging vector of locally aggregated descriptor (VLAD)

来源：评论

学校读者我要写书评

暂无评论

FusionNet for interactive image segmentation 7th

FusionNet for Interactive Image Segmentation

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Wu, Enyi Shi, Qingxuan Wang, Kanglin Hebei Univ Sch Cyber Secur & Comp Baoding 071002 Peoples R China Hebei Univ Hebei Machine Vis Engn Res Ctr Baoding 071002 Peoples R China

ISBN: (纸本)9789819784899;9789819784905

Despite the advancements in neural network technologies driving interactive image segmentation forward, challenges persist, especially concerning segmentation ambiguities caused by overlapping or visually similar objects against complex backgrounds, as well as intricate object boundaries. Addressing these challenges, we introduce FusionNet, focusing on effective feature fusion. Firstly, the Hierarchical Context Fusion Module aids in grasping holistic structures and multi-scale contextual information of target objects. Secondly, the Attention Feature Fusion Module captures more representative feature expressions. This design empowers FusionNet to capture details and contextual relationships better, thereby enhancing segmentation accuracy. For fine-grained boundary details, we propose the Local Correction Module, refining local mask details meticulously. This module initially focuses on information around newly clicked areas, employing discriminative correction feedback for enhanced detail processing accuracy. Rigorous experimentations on datasets like SBD, DAVIS, GrabCut, and Berkeley validate our model's effectiveness, with segmentation results strongly supporting the superiority of our approach.

关键词： interactive image segmentation Feature fusion Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：